An Efficient Dorsal Hand Vein Recognition Based on Firefly Algorithm

Abstract

Biometric technology is an efficient personal authentication and
identification technique. As one of the main-stream branches, dorsal hand
vein recognition has been recently attracted the attention of researchers. It is more preferable than the other types of biometrics becuse it’s impossible to steal or counterfeit the patterns and the pattern of the vessels of back of the hand is fixed and unique with repeatable biometric features. Also, the recent researches have been obtained no certain recognition rate yet becuse of the noises in the imaging patterns, and impossibility of Dimension reducing because of the non-complexity of the models, and proof of correctness of identification is required. Therefore, in this paper, first, the images of blood vessels on back of the hands of people is analysed, and after pre-processing of images and feature extraction (in the intersection between the vessels) we began to identify people using firefly clustering algorithms. This identification is done based on the distance patterns between crossing vessels and their matching place. The identification will be done based on the classification of each part of NCUT data set and it consisting of 2040 dorsal hand vein images. High speed in patterns recognition and less computation are the advantages of this method. The recognition rate of this method is
more accurate and the error is less than one percent. At the end the
correctness percentage of this method (CLU-D-F-A) for identification is
compared with other various algorithms, and the superiority of the proposed method is proved.

DOI:http://dx.doi.org/10.11591/ijece.v3i1.1760